用非负核回归提升图分类可解释性，避免传统模型依赖线性分类器
GraphNNK -- Graph Classification and Interpretability
- 采用非负核回归替代传统线性分类器，基于相似样本的凸组合进行预测
- 在多个图数据集上实现与主流GNN相当的分类准确率
- 提供直观的决策解释，适合需要可解释性的工业应用
图神经网络（GNN）已成为图结构数据学习的标准方法。然而，其对参数化分类器（通常是线性Softmax层）的依赖限制了可解释性，并可能影响泛化能力。最近关于基于插值的方法，特别是非负核回归（NNK），表明预测可表示为嵌入空间中相似训练样本的凸组合，既获得理论支持，也提供可解释性解释。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have become a standard approach for learning from graph-structured data. However, their reliance on parametric classifiers (most often linear softmax layers) limits interpretability and sometimes hinders generalization. Recent work on interpolation-based methods, particularly Non-Negative Kernel regression (NNK), has demonstrated that predictions can be expressed as convex combinations of similar training examples in the embedding space, yielding both theoretical results and interpretable explanations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。